Triple
T15242017
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Blue Light Special |
E364278
|
entity |
| Predicate | promotionChannel |
P37056
|
FINISHED |
| Object | brick-and-mortar stores |
—
|
LITERAL FINISHED |
How this triple was built (2 steps)
Every LLM step that produced this triple, in pipeline order — named-entity classification, the disambiguation choices (the exact options shown, with the pick highlighted), and the generated description. The batch + timestamp of each is in the Provenance table below.
NER
Named-entity recognition
gpt-5-mini
Instruction
Given a phrase, classify it is english named entity (e.g., persons, organizations, works of art) in Latin script, or not (e.g., literals, dates, URLs, verbose phrases). For disambiguation, the statement where the phrase occurs as object is also given. Please return a JSON object with `phrase` (string, the phrase being analyzed) and `is_ne` (boolean, indicating whether the phrase is a Named Entity).
Input
Phrase: brick-and-mortar stores | Statement: [Blue Light Special, promotionChannel, brick-and-mortar stores]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: promotionChannel Context triple: [Blue Light Special, promotionChannel, brick-and-mortar stores]
-
A.
promotionBetween
Indicates a relationship where one entity advances or elevates another entity’s status, rank, or visibility relative to a previous state.
-
B.
promotionFrom
Indicates that an entity has been elevated in position, rank, or status from a specified prior role or level.
-
C.
promotionMethod
chosen
Indicates the method or channel through which something (such as a product, service, or content) is promoted or advertised.
-
D.
promotionPath
Indicates the career advancement relationship showing how one role or position can lead or progress to another.
-
E.
promotionType
Indicates the specific kind or category of promotion associated with an entity or event.
- F. None of above.
Provenance (3 batches)
The batch behind each pipeline step, in order, with when it ran. Timestamps are batch-level — stages were processed in waves, so the object chain (NER → NED1 → NEDg → NED2) reads in order, but predicate / elicitation batches can sit in a different wave.
| Step | Stage | Batch ID | Status | When |
|---|---|---|---|---|
| creating | Elicitation | batch_69d85a0dde7481908fc64d1e82d5d20d |
completed | April 10, 2026, 2:01 a.m. |
| NER | Named-entity recognition | batch_69e007dcc33081908545ea1a1d2c19fe |
completed | April 15, 2026, 9:49 p.m. |
| PD | Predicate disambiguation | batch_69deca899d5c8190be4a7c71e1683c69 |
completed | April 14, 2026, 11:15 p.m. |
Created at: April 10, 2026, 3:13 a.m.